]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
David Zafman [Tue, 18 Nov 2014 21:00:15 +0000 (13:00 -0800)]
ceph_objectstore_tool: Add feature called set-allow-sharded-objects
Uses --op set-allow-sharded-objects option
This operation will be rejected if on the target OSD's osdmap there is
at least one OSD which does not support ERASURE CODES.
Prompt the user that they could import if sharded state allowed
Prompt the user to use new feature if sharded state found inconsistent
Fixes: #10077
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Tue, 18 Nov 2014 19:59:18 +0000 (11:59 -0800)]
ceph_objectstore_tool: Add utility routine get_osdmap()
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Thu, 13 Nov 2014 05:14:11 +0000 (21:14 -0800)]
ceph_objectstore_tool: Clear ...INCOMPAT_SHARDS from feature if exporting replicated pg
Don't require importing OSD to have shards feature for replicated pg
http://tracker.ceph.com/issues/10077 Fixes: #10077
Signed-off-by: David Zafman <dzafman@redhat.com>
Loic Dachary [Tue, 18 Nov 2014 12:46:10 +0000 (13:46 +0100)]
Merge pull request #2951 from sponce/master
Fixed trivial locking issue in the trunc method of libradosstriper
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Tue, 18 Nov 2014 11:17:00 +0000 (12:17 +0100)]
Merge pull request #2910 from swamireddy/wip-organizationmap
mailmap updates
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Tue, 18 Nov 2014 11:15:58 +0000 (12:15 +0100)]
Merge pull request #2907 from xuechendi/update_organizationmap
Add myself to <contact@intel.com>
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Sebastien Ponce [Tue, 18 Nov 2014 09:30:36 +0000 (10:30 +0100)]
Fixed locking issue in the trun method of libradosstriper leading to potential race conditions - Fixes: #10129
Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
Loic Dachary [Tue, 18 Nov 2014 10:12:59 +0000 (11:12 +0100)]
Merge pull request #2917 from leseb/rbd-update-glance-config
doc: update the OpenStack glance configuration
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Tue, 18 Nov 2014 09:40:55 +0000 (10:40 +0100)]
Merge pull request #2950 from ceph/wip-10128
Wip 10128
Reviewed-by: Loic Dachary <ldachary@redhat.com>
David Zafman [Tue, 18 Nov 2014 08:10:41 +0000 (00:10 -0800)]
tests: ceph_objectstore_tool.py test all variants of export/import
Handle change of error message text
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Tue, 18 Nov 2014 07:23:40 +0000 (23:23 -0800)]
ceph_objectstore_tool: Make --file option consistent by treating "-" as stdout/stdin
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Tue, 18 Nov 2014 07:02:50 +0000 (23:02 -0800)]
ceph_objectstore_tool: When exporting to stdout, don't cout messages
Fixes: #10128
Caused by
a2bd2aa7
Signed-off-by: David Zafman <dzafman@redhat.com>
Sage Weil [Tue, 18 Nov 2014 06:33:41 +0000 (22:33 -0800)]
Merge pull request #2946 from ceph/wip-execstack
Add annotation to all assembly files to turn off stack-execute bit
Reviewed-by: Sage Weil <sage@redhat.com>
Josh Durgin [Tue, 18 Nov 2014 02:23:27 +0000 (18:23 -0800)]
Merge pull request #2933 from ceph/wip-librbd-symbols
librbd: Only public API symbols from the shared library
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Sage Weil [Mon, 17 Nov 2014 23:44:38 +0000 (15:44 -0800)]
Merge pull request #2947 from HP-Scale-out-Storage/wip-10096
Wip 10096 (ceph-disk umount race condition)
Reviewed-by: Sage Weil <sage@redhat.com>
Blaine Gardner [Mon, 17 Nov 2014 23:17:15 +0000 (17:17 -0600)]
Fix bug #10096 (ceph-disk umount race condition)
Bug: http://tracker.ceph.com/issues/10096
Brief: Unmounting temporary mount point failed due to file being 'busy'.
Root cause could not be easily determined due to timing variances caused
by debug attempts. Race condition exists.
Solution: Implement a retry with incremental backoff as a viable
workaround. This workaround is okay because (1) Finding the root cause
would take a not insignificant amount of time/effort. (2) The workaround
is a more general fix for any process that might cause the exhibited
behavior.
Signed-off-by: Blaine Gardner <blaine.gardner@hp.com>
João Eduardo Luís [Mon, 17 Nov 2014 18:03:35 +0000 (18:03 +0000)]
Merge pull request #2914 from dachary/wip-10093-monstore-tool
mon: ceph-monstore-tool must close()
Reviewed-by: Joao Eduardo Luis <joao@redhat.com>
Sage Weil [Mon, 17 Nov 2014 14:57:58 +0000 (06:57 -0800)]
Merge pull request #2943 from ceph/wip-dumper-coverity
tools: Close the fd before returning in Dumper
Reviewed-by: Sage Weil <sage@redhat.com>
Loic Dachary [Mon, 17 Nov 2014 13:31:07 +0000 (14:31 +0100)]
Merge pull request #2942 from tchaikov/wip-fix-rongze-affiliation
mailmap: fix Rongze's affiliation
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Kefu Chai [Mon, 17 Nov 2014 12:50:30 +0000 (20:50 +0800)]
mailmap: fix Rongze's affiliation
Loic Dachary [Mon, 17 Nov 2014 11:29:58 +0000 (12:29 +0100)]
Merge pull request #2915 from dachary/wip-10063-objectstore-tool-erasure-code
ghobject::dump must display shard_id + make ceph_objectstore_tool run from make check
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Mon, 17 Nov 2014 10:28:07 +0000 (11:28 +0100)]
Merge pull request #2929 from thesues/master
Fix libstriprados::stat, use strtoll insdead of strtol
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Dongmao Zhang [Fri, 14 Nov 2014 10:48:58 +0000 (18:48 +0800)]
Fix libstriprados::stat, use strtoll insdead of strtol
The return value(long int) of strict_strtol is too small for unstriped
object.
Signed-off-by: Dongmao Zhang <deanraccoon@gmail.com>
Sage Weil [Sun, 16 Nov 2014 23:23:39 +0000 (15:23 -0800)]
Merge pull request #2939 from aspiers/fix/architecture-docs
minor tweaks to architecture document
Reviewed-by: Sage Weil <sage@redhat.com>
Adam Spiers [Sun, 16 Nov 2014 20:52:36 +0000 (15:52 -0500)]
doc: fix typos in diagram for incomplete write
In this example of a write of v2 of the object being interrupted, OSD2
would never have any version of the D1 chunk. It only has the old v1
version of the D2 chunk.
Signed-off-by: Adam Spiers <aspiers@suse.com>
Adam Spiers [Sun, 16 Nov 2014 20:51:16 +0000 (15:51 -0500)]
doc: fix incorrect equalities
The previous punctuation accidentally implied that K == 1 and M == -1.
Signed-off-by: Adam Spiers <aspiers@suse.com>
Adam Spiers [Sun, 16 Nov 2014 20:49:03 +0000 (15:49 -0500)]
doc: fix typo (superfluous "no")
Signed-off-by: Adam Spiers <aspiers@suse.com>
David Zafman [Sat, 15 Nov 2014 19:43:10 +0000 (11:43 -0800)]
tests: ceph_objectstore_tool.py fix list-attr for erasure code
Adding testing of xattr for erasure coded shards
Fix error message when finding an unexpected xattr key
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Sat, 15 Nov 2014 19:46:15 +0000 (11:46 -0800)]
tests: ceph_objectstore_tool.py check for malformed JSON for erasure code objs
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman [Sat, 15 Nov 2014 19:44:54 +0000 (11:44 -0800)]
tests: ceph_objectstore_tool.py fix off by 1 ATTR_OBJS handling
Signed-off-by: David Zafman <dzafman@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 00:16:10 +0000 (01:16 +0100)]
common: do not omit shard when ghobject NO_GEN is set
Do not silence the display of shard_id when generation is NO_GEN.
Erasure coded objects JSON representation used by ceph_objectstore_tool
need the shard_id to find the file containing the chunk.
Minimal testing is added to ceph_objectstore_tool.py
http://tracker.ceph.com/issues/10063 Fixes: #10063
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:33:42 +0000 (17:33 +0100)]
tests: run ceph_objectstore_tool.py from make check
http://tracker.ceph.com/issues/10064 Fixes: #10064
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 10:00:17 +0000 (11:00 +0100)]
tests: ceph_objectstore_tool.py skip if /dev/tty fails
Some environments do not have a /dev/tty. When opening /dev/tty fails,
skip the test instead of returning an error.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 18:15:50 +0000 (19:15 +0100)]
tests: ceph_objectstore_tool.py encapsulate init-ceph stop
Call init-ceph in kill_daemons and add a call to kill_daemon when main
returns on error so that it never leaves daemons hanging.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 18:14:49 +0000 (19:14 +0100)]
tests: ceph_objectstore_tool.py main returns
Instead of calling sys.exit() the main function returns the desired exit
code.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:32:14 +0000 (17:32 +0100)]
tests: ceph_objectstore_tool.py replace stop.sh with init-ceph
The stop.sh will stop all ceph-* processes. Use the init-ceph script
instead to selectively kill the daemons run by the vstart.sh cluster
used for ceph_objectstore_tool.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:30:29 +0000 (17:30 +0100)]
tests: ceph_objectstore_tool.py use a dedicated directory
Set CEPH_DIR to a directory that is specific to ceph_objectstore_tool so
that it can run in parallel with other vstart.sh clusters.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:27:01 +0000 (17:27 +0100)]
tests: ceph_objectstore_tool.py run faster by default
By default use only a small number of objects to speed up the tests. If
the argument "big" is given, use a large number of objects as it may
help find some problems.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:21:48 +0000 (17:21 +0100)]
tests: ceph_objectstore_tool.py run mon and osd on specific port
By default vstart.sh runs MDS but they are not needed for the tests,
only run mon and osd instead. Instead of using the default vstart.sh
port which may conflict with a already running vstart.sh, set the
CEPH_PORT=7400 which is not used by any other test run with make check.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:16:41 +0000 (17:16 +0100)]
tests: ceph_objectstore_tool.py can use a WARN cluster
The tests do not need HEALTH_OK exclusively, a HEALTH_WARN cluster can
also run them successfully.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 16:12:35 +0000 (17:12 +0100)]
tests: ceph_objectstore_tool.py use env python
Using #/usr/bin/env python instead of a hard coded path is more flexible
and can also be used to run from virtualenv.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 17:49:10 +0000 (18:49 +0100)]
vstart: use hostname -s instead of fqdn
Otherwise init-ceph.in will fail if hostname returns a fqdn. It
validates the host entry of the [osd.x] section does not contain dots.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Dan Mick [Sat, 15 Nov 2014 01:59:57 +0000 (17:59 -0800)]
Add annotation to all assembly files to turn off stack-execute bit
See discussion in http://tracker.ceph.com/issues/10114
Building with these changes allows output from readelf like this:
$ readelf -lW src/.libs/librados.so.2 | grep GNU_STACK
GNU_STACK 0x000000 0x0000000000000000 0x0000000000000000 0x000000
0x000000 RW 0x8
(note the absence of 'X' in 'RW')
Fixes: #10114
Signed-off-by: Dan Mick <dan.mick@redhat.com>
Greg Farnum [Fri, 14 Nov 2014 22:28:25 +0000 (14:28 -0800)]
tools: Close the fd before returning in Dumper
CID
1251577
CID 717084
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 21:46:28 +0000 (22:46 +0100)]
Merge pull request #2935 from dachary/wip-mailmap
mailmap: Loic Dachary name normalization
Loic Dachary [Fri, 14 Nov 2014 21:42:24 +0000 (22:42 +0100)]
mailmap: Loic Dachary name normalization
Do not rewrite the past.
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Sage Weil [Fri, 14 Nov 2014 18:37:10 +0000 (10:37 -0800)]
test_async_driver: fix warning
test/msgr/test_async_driver.cc:233:209: instantiated from here
Signed-off-by: Sage Weil <sage@redhat.com>
John Wilkins [Fri, 14 Nov 2014 18:13:12 +0000 (10:13 -0800)]
Merge pull request #2389 from ceph/wip-doc-documenting-ceph
doc: Update documenting ceph to include CentOS/RHEL
Reviewed-by: John Wilkins <jowilkin@redhat.com>
John Wilkins [Fri, 14 Nov 2014 18:11:35 +0000 (10:11 -0800)]
doc: Removed separate build file for rpm.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Yehuda Sadeh [Fri, 14 Nov 2014 17:03:42 +0000 (09:03 -0800)]
Merge pull request #2801 from CzBiX/permanent-location
rgw: add location when data in another region.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 16:18:12 +0000 (17:18 +0100)]
Merge pull request #2932 from nilamdyuti/wip-doc-documenting-ceph
doc: Adds build-doc guidelines for Fedora and CentOS/RHEL.
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Haomai Wang [Fri, 14 Nov 2014 16:12:05 +0000 (00:12 +0800)]
Merge pull request #2930 from dachary/wip-warning
tests: fix cast compilation warning
Nilamdyuti Goswami [Fri, 14 Nov 2014 15:36:15 +0000 (21:06 +0530)]
doc: Adds build-doc guidelines for Fedora and CentOS/RHEL.
Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 15:17:54 +0000 (16:17 +0100)]
Merge pull request #2923 from ktdreyer/doc-install-giant
doc: update packages page for Giant
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Ken Dreyer [Thu, 13 Nov 2014 23:20:14 +0000 (16:20 -0700)]
doc: update release descriptions on packages page
Firefly was listed as the "latest release" of Ceph. Add Giant and label
it as the latest release instead.
Releases A-C and E are no longer supported. D will receive updates for
some time longer, and F is a "long term stable" release.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 14:01:34 +0000 (15:01 +0100)]
tests: fix cast compilation warning
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 10:05:02 +0000 (11:05 +0100)]
Merge pull request #2928 from leseb/improve-exceptions
Improve readability of the exception
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Sébastien Han [Thu, 13 Nov 2014 18:11:36 +0000 (19:11 +0100)]
Improve readability of the exception
The error messages were not really clear from a non-programmer
perspective. In the context of OpenStack all the drivers are falling
back to the exceptions provided by the rados library. Having clearer
error messages will help debugging misconfigured environment.
Signed-off-by: Sébastien Han <sebastien.han@enovance.com>
VRan Liu [Fri, 14 Nov 2014 08:27:17 +0000 (16:27 +0800)]
rgw: add location when data in another region.
When the bucket of requested is in another region, Add location header
in response, so client can follow that to get data.
Signed-off-by: VRan Liu <gliuwr@gmail.com>
Sébastien Han [Thu, 13 Nov 2014 17:24:07 +0000 (18:24 +0100)]
doc: update the OpenStack glance configuration
Juno is now using a section for configuring the stores, so let's use it.
Put spaces between flag and value for clarity and readibility.
Signed-off-by: Sébastien Han <sebastien.han@enovance.com>
Jason Dillaman [Fri, 14 Nov 2014 06:02:48 +0000 (01:02 -0500)]
librbd: Only public API symbols from the shared library
The librbd shared library was previously exporting all
symbols. librbd public API methods are now explicitly
exported and all other symbols are hidden.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Loic Dachary [Fri, 14 Nov 2014 07:42:35 +0000 (08:42 +0100)]
Merge pull request #2925 from yuyuyu101/update-mailmap
Mailmap: add Rongze organization
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Haomai Wang [Fri, 14 Nov 2014 03:42:41 +0000 (11:42 +0800)]
Mailmap: add Rongze organization
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Sage Weil [Fri, 14 Nov 2014 00:41:34 +0000 (16:41 -0800)]
vstart.sh: complain less about fullish mon disks
Lots of people develop on file systems > 70% full.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 13 Nov 2014 21:26:04 +0000 (13:26 -0800)]
Merge remote-tracking branch 'gh/next'
Yan, Zheng [Thu, 13 Nov 2014 05:38:35 +0000 (13:38 +0800)]
mds: don't overwrite reply's snapbl
set_trace_dist() updates reply's snapbl, don't overwrite it. For MKSNAP
request, just need to set mdr->tracei, set_trace_dist() will set reply's
snapbl.
Reviewed-by: Sage Weil <sage@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 20:58:45 +0000 (21:58 +0100)]
Merge pull request #2772 from ceph/wip-init-radosgw
init-radosgw.sysv: set ulimit -n before starting daemon
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Samuel Just [Thu, 13 Nov 2014 19:08:23 +0000 (11:08 -0800)]
Merge pull request #2920 from ceph/wip-10095
crush: fix detach_bucket
Reviewed-by: Samuel Just <sjust@redhat.com>
Sage Weil [Thu, 13 Nov 2014 18:59:22 +0000 (10:59 -0800)]
crush/CrushWrapper: fix detach_bucket
In commit
9850227d2f0ca2f692a154de2c14a0a08e751f08 we changed the call that
changed the weight of all instances of item to one that explicitly
changes it in the parent bucket, but parent_id may not be valid at the
call site. Move this into the conditional block to fix.
Fixes: #10095
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 13 Nov 2014 18:49:33 +0000 (10:49 -0800)]
Makefile: include 'ceph' in base target
This makes 'make base' enough to vstart.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 13 Nov 2014 18:35:04 +0000 (10:35 -0800)]
Merge pull request #2906 from ceph/wip-9835
osd: fix misdirected ec ops stuck in optracker (9835)
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Thu, 13 Nov 2014 18:05:53 +0000 (10:05 -0800)]
msg/Makefile: add new header to tarball
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 13 Nov 2014 17:12:26 +0000 (09:12 -0800)]
Merge pull request #2909 from yuyuyu101/wip-10079
AsyncMessenger: Add select support and tests for async drivers
Swami Reddy [Wed, 12 Nov 2014 17:10:42 +0000 (22:40 +0530)]
mailmap: Dan Mick name normalization
Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
Swami Reddy [Wed, 12 Nov 2014 16:56:48 +0000 (22:26 +0530)]
mailmap: Xan Peng affiliation
Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
Swami Reddy [Wed, 12 Nov 2014 16:54:00 +0000 (22:24 +0530)]
mailmap: BJ Lougee affiliation
Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
Swami Reddy [Wed, 12 Nov 2014 16:51:01 +0000 (22:21 +0530)]
mailmap: Derrick Schneider affiliation
Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
Swami Reddy [Wed, 12 Nov 2014 16:46:51 +0000 (22:16 +0530)]
mailmap: Federico Gimenez name normalization
Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
Loic Dachary [Thu, 13 Nov 2014 14:37:48 +0000 (15:37 +0100)]
mon: ceph-monstore-tool must close()
Otherwise it asserts because the destructor checks for the is_open flag.
http://tracker.ceph.com/issues/10093 Fixes: #10093
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Jason Dillaman [Thu, 13 Nov 2014 14:26:02 +0000 (09:26 -0500)]
Merge pull request #2912 from dachary/wip-warning
tests: fix compilation warning
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 12:45:02 +0000 (13:45 +0100)]
Merge pull request #2911 from keichwa/wip-doc-rados
Wip doc rados
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loic Dachary [Thu, 13 Nov 2014 12:03:22 +0000 (13:03 +0100)]
tests: fix compilation warning
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Karl Eichwalder [Thu, 13 Nov 2014 10:40:05 +0000 (11:40 +0100)]
doc: remove superfluous white spaces (for testing)
Signed-off-by: Karl Eichwalder <ke@suse.de>
Karl Eichwalder [Thu, 13 Nov 2014 10:17:01 +0000 (11:17 +0100)]
doc: Fix 2 syntax errors.
Signed-off-by: Karl Eichwalder <ke@suse.de>
Haomai Wang [Thu, 13 Nov 2014 07:10:05 +0000 (15:10 +0800)]
AsyncMessenger: Fix select driver for add_event
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Haomai Wang [Thu, 13 Nov 2014 05:43:27 +0000 (13:43 +0800)]
AsyncMessenger: Add tests for async drivers
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Haomai Wang [Wed, 12 Nov 2014 09:26:03 +0000 (17:26 +0800)]
AsyncMessenger: Support select for other OS such as Windows
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Sage Weil [Thu, 13 Nov 2014 01:11:10 +0000 (17:11 -0800)]
osd/OSD: use OSDMap helper to determine if we are correct op target
Use the new helper. This fixes our behavior for EC pools where targetting
a different shard is not correct, while for replicated pools it may be. In
the EC case, it leaves the op hanging indefinitely in the OpTracker because
the pgid exists but as a different shard.
Fixes: #9835
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 13 Nov 2014 01:04:35 +0000 (17:04 -0800)]
osd/OSDMap: add osd_is_valid_op_target()
Helper to check whether an osd is a given op target for a pg. This
assumes that for EC we always send ops to the primary, while for
replicated we may target any replica.
Signed-off-by: Sage Weil <sage@redhat.com>
Chendi.Xue [Wed, 12 Nov 2014 20:29:57 +0000 (04:29 +0800)]
Add myself to <contact@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
David Zafman [Wed, 12 Nov 2014 23:22:04 +0000 (15:22 -0800)]
ceph_objectstore_tool: Fixes to make import work again
The is_pg() call is now true even for pgs pending removal, fix broken
finish_remove_pgs() by removing is_pg() check.
Need to add create_collection() to the initial transaction on import
Fixes: #10090
Signed-off-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 12 Nov 2014 21:58:14 +0000 (13:58 -0800)]
Merge pull request #2903 from ceph/wip-crush-tree
crush: fix tree bucket functions
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 12 Nov 2014 21:35:43 +0000 (13:35 -0800)]
vstart.sh: warn less
Signed-off-by: Sage Weil <sage@redhat.com>
Josh Durgin [Wed, 12 Nov 2014 20:57:06 +0000 (21:57 +0100)]
Merge pull request #2892 from leseb/doc-juno-client-socket
doc: enable RBD cache and socket on OpenStack deployments
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Sage Weil [Wed, 12 Nov 2014 19:27:08 +0000 (11:27 -0800)]
Merge pull request #2902 from dachary/wip-10083-noisy-osd
qa: handle CEPH_CLI_TEST_DUP_COMMAND on ceph osd create
Reviewed-by: Sage Weil <sage@redhat.com>
Josh Durgin [Wed, 12 Nov 2014 19:18:52 +0000 (11:18 -0800)]
Merge remote-tracking branch 'origin/next'
Loic Dachary [Wed, 12 Nov 2014 17:49:54 +0000 (18:49 +0100)]
qa: handle CEPH_CLI_TEST_DUP_COMMAND on ceph osd create
If CEPH_CLI_TEST_DUP_COMMAND is set when ceph osd create is called, it
will create two osd. They must be cleaned up afterwards instead of
assuming only one is going to be created.
http://tracker.ceph.com/issues/10083 Fixes: #10083
Signed-off-by: Loic Dachary <ldachary@redhat.com>
Sage Weil [Wed, 12 Nov 2014 18:02:52 +0000 (10:02 -0800)]
Merge pull request #2124 from ceph/wip-objectstore
simplify ObjectStore interface
sage-2014-11-11_08:26:01-rados-wip-sage-testing-distro-basic-multi
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Reviewed-by: Samuel Just <sjust@redhat.com>
Sage Weil [Wed, 12 Nov 2014 18:01:50 +0000 (10:01 -0800)]
Merge pull request #2722 from ceph/wip-9598
msgr: make mark_down not block on fast dispatch
sage-2014-11-11_08:26:01-rados-wip-sage-testing-distro-basic-multi
Reviewed-by: Greg Farnum <greg@inktank.com>
John Wilkins [Wed, 12 Nov 2014 17:18:42 +0000 (09:18 -0800)]
Merge pull request #2901 from ktdreyer/doc-spelling-grammar
doc: spelling & grammar fixes
Reviewed-by: John Wilkins <jowilkin@redhat.com>